Librarian
Inspired by USV's Librarian agent (https://blog.usv.com/meet-the-agents), rebuilt as a generic version for any team that keeps a folder of who and what it tracks — not just a VC deal log. Reads every meeting note already sitting in the same entity folder meeting-scribe writes to, groups them by recurring idea, and reports as a theme only an idea that shows up in at least two distinct meeting notes. A single mention in one meeting is never reported as a theme, and a run that finds nothing above the bar says so plainly rather than padding the output. Every theme carries a working title, a short draft post body, and a Sources list naming every meeting note and quote it's grounded in. It never re-matches a name against the entity folder, never writes to people, organizations, or meeting files, and never publishes anything — every draft is a local markdown file for a human to review, edit, and post themselves. Includes an eval contract with self-tests covering the two-meeting theme bar, the lookback window, and the never-publishes boundary.
First-party, by Skills and Agents Co
September 4, 2026
Simple install — no setup required
Open the Claude desktop app and go to the Project you want this in
Go to Code, then Customize, then click Create a new skill and upload the skill file below
Say a trigger phrase to activate it
Download the skill file below
In ChatGPT, create a Project and attach the file (or paste its contents into the project instructions). For a reusable setup, build a Custom GPT via Explore GPTs → Create and add the file there
Start a chat in that Project or GPT, then say a trigger phrase to activate it
Download the skill file below
Place it at .cursor/skills/librarian/SKILL.md (rename the downloaded file to SKILL.md). The shared .agents/skills/librarian/SKILL.md path also works
Cursor loads the skill when your task matches its description. Say a trigger phrase to activate it
Download the skill file below
Place it at .github/skills/librarian/SKILL.md in your repository (rename the downloaded file to SKILL.md)
Copilot loads the skill when it is relevant to your task. Say a trigger phrase to activate it
Download the skill file below
Place it at .agents/skills/librarian/SKILL.md in your repository (rename the downloaded file to SKILL.md)
Codex loads the skill when your task matches, or invoke it explicitly with /skills. Say a trigger phrase to activate it
Download the skill file below
In Gemini, create a Gem, then upload the skill file as a knowledge file
Copy the Gem instructions with the button below, then paste them into the instructions box
Start a chat with the Gem, then say a trigger phrase to activate it
You are a Gem built around the "Librarian" skill. Reads the meeting notes and mention history already sitting in your tracked entity folder, finds the ideas that keep recurring across more than one meeting, and drafts a short post for each one — grounded in quotes from the meetings it came from. Read the attached file first, then follow its instructions. Activate this skill when the user says something like: run librarian, find recurring themes in my meetings, what keeps coming up, draft some posts from my meeting notes, distill my meetings into content ideas.
npx skills add skills-agents-co/skills-and-agents-library/librarianYour skill is downloading.
Get an email when we ship new skills and updates.
You're on the list. We'll email you when new skills drop.
What this skill does
This is an overview of the skill from the site, not the skill's real instructions. The full SKILL.md Claude reads when this skill is active lives on GitHub at the source below.
Inspired by USV’s Librarian agent — USV built theirs to surface recurring threads across a VC deal log. This is a generic, independently built version, not their code: any team that keeps files on people, organizations, or meetings can point this at the entity folder and get the same shape of output.
Reads every meeting note already sitting in the same entity folder meeting-scribe writes to, groups them by recurring idea, and reports as a theme only an idea that shows up in at least two distinct meeting notes (configurable). Each theme gets a working title, a short draft post body, and a Sources list naming every meeting note and quote it’s grounded in — no quote, no theme. A single mention in one meeting is never reported as a theme, and a run that finds nothing above the bar says so plainly rather than padding the output. By default it reads the last 90 days of meeting notes; anything older is excluded and named in the run summary rather than silently dropped. It’s read-only against the entity folder and never publishes anything — every draft lands under its own posts folder for a human to review, edit, and post themselves.
View full SKILL.md on GitHub